Security audit
Deep Cognition
Security checks across malware telemetry and agentic risk
Overview
This skill is a writing-guidance template that does not request system access, credentials, commands, or background behavior.
This appears low-risk and purpose-aligned. Installing it may influence an agent's article-writing style and framing, but it does not grant extra system access or perform actions outside generating prose.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.